Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes
Sridhar Mahadevan and Mauro Maggioni

Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes.pdf 1.34MB
Type: Paper
Tags:

Metadata: 
@article{8:74,author={Sridhar Mahadevan and Mauro Maggioni}, Title={Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes},journal={Journal of Machine Learning Research},volume={8}, url={http://www.jmlr.org/papers/volume8/mahadevan07a/mahadevan07a.pdf}}
Citation:
Mahadevan, S. & Maggioni, M.. (2014). Proto-value Functions: A Laplacian Framework for Learning Representation and Control in Markov Decision Processes [Data set]. Academic Torrents. https://academictorrents.com/details/cca65715cb31b53876c27c0f4ddcd2be9ad7036a
No stats to report yet.
Related Torrents
Report
Send Feedback Start
   0.000010
DB Connect
   0.000575
Lookup hash in DB
   0.000473
Get torrent details
   0.000147
Get torrent details, finished
   0.000266
Get authors
   0.000001
Select authors
   0.000190
Parse bibtex
   0.000134
Write header
   0.000289
get stars
   0.000133
home tab
   0.000134
render right panel
   0.000006
render ads
   0.000492
fetch current hosters
   0.000289
Start get stats
   0.000374
End get stats
   0.000003
related datasets
   0.002426
Done